1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
|
#!/usr/local/bin/python
""" HTML - tag a HTML string (Version 0.6)
Copyright (c) 2000, Marc-Andre Lemburg; mailto:mal@lemburg.com
Copyright (c) 2000-2014, eGenix.com Software GmbH; mailto:info@egenix.com
See the documentation for further information on copyrights,
or contact the author. All Rights Reserved.
"""
import sys
# constants + engine
from mx.TextTools import *
# ErrorTag
error = '*syntax error' # error tag obj
tagname_charset = CharSet(alpha+'\-'+number)
tagattrname_charset = CharSet(alpha+'\-'+number)
tagvalue_charset = CharSet('^"\'> ')
white_charset = CharSet(' \r\n\t')
tagname_charset = CharSet(alpha+'\-'+number)
tagattrname_charset = CharSet(alpha+'\-'+number)
tagvalue_charset = CharSet('^"\'> ')
white_charset = CharSet(' \r\n\t')
tagattr = (
# name
('name',AllInCharSet,tagattrname_charset),
# with value ?
(None,Is,'=',MatchOk),
# skip junk
(None,AllInCharSet,white_charset,+1),
# unquoted value
('value',AllInCharSet,tagvalue_charset,+1,MatchOk),
# double quoted value
(None,Is,'"',+5),
('value',AllNotIn,'"',+1,+2),
('value',Skip,0),
(None,Is,'"'),
(None,Jump,To,MatchOk),
# single quoted value
(None,Is,'\''),
('value',AllNotIn,'\'',+1,+2),
('value',Skip,0),
(None,Is,'\'')
)
valuetable = (
# ignore whitespace + '='
(None,AllInCharSet,CharSet(' \r\n\t='),+1),
# unquoted value
('value',AllInCharSet,tagvalue_charset,+1,MatchOk),
# double quoted value
(None,Is,'"',+5),
('value',AllNotIn,'"',+1,+2),
('value',Skip,0),
(None,Is,'"'),
(None,Jump,To,MatchOk),
# single quoted value
(None,Is,'\''),
('value',AllNotIn,'\'',+1,+2),
('value',Skip,0),
(None,Is,'\'')
)
allattrs = (
# look for attributes
(None,AllInCharSet,white_charset,+4),
(None,Is,'>',+1,MatchOk),
('tagattr',Table,tagattr),
(None,Jump,To,-3),
(None,Is,'>',+1,MatchOk),
# handle incorrect attributes
(error,AllNotIn,'> \r\n\t'),
(None,Jump,To,-6)
)
# NOTE: The htmltag tag table assumes that the input text is given
# in upper case letters (see <XMP> handling).
htmltag = (
(None,Is,'<'),
# is this a closing tag ?
('closetag',Is,'/',+1),
# a coment ?
('comment',Is,'!',+8),
(None,Word,'--',+4),
('text',WordStart,'-->',+1),
(None,Skip,3),
(None,Jump,To,MatchOk),
# a SGML-Tag ?
('other',AllNotIn,'>',+1),
(None,Is,'>'),
(None,Jump,To,MatchOk),
# XMP-Tag ?
('tagname',Word,'XMP',+5),
(None,Is,'>'),
('text',WordStart,'</XMP>'),
(None,Skip,len('</XMP>')),
(None,Jump,To,MatchOk),
# get the tag name
('tagname',AllInCharSet,tagname_charset),
# look for attributes
(None,AllInCharSet,white_charset,+4),
(None,Is,'>',+1,MatchOk),
('tagattr',Table,tagattr),
(None,Jump,To,-3),
(None,Is,'>',+1,MatchOk),
# handle incorrect attributes
(error,AllNotIn,'> \n\r\t'),
(None,Jump,To,-6)
)
htmltable = (# HTML-Tag
('htmltag',Table,htmltag,+1,+4),
# not HTML, but still using this syntax: error or inside XMP-tag !
(error,Is,'<',+3),
(error,AllNotIn,'>',+1),
(error,Is,'>'),
# normal text
('text',AllNotIn,'<',+1),
# end of file
('eof',EOF,Here,-5),
)
if __name__ == '__main__':
t = TextTools._timer()
# read file
f = open(sys.argv[1])
text = f.read()
try:
count = int(sys.argv[2])
except:
count = 1000
print 'Starting to parse the file %i times...' % count
# parse file
t.start()
for i in range(count):
utext = upper(text)
result, taglist, nextindex = tag(utext,htmltable)
if not result:
print ' parsing failed; aborting'
break
t = t.stop()[0]
mean = t/count
print result, nextindex, mean*1000,'msec',nextindex/mean,'bytes/sec.'
print
print 'Hit return to see the tags...'
raw_input()
print
print_tags(text,taglist)
|
